Model comparison
Llama 3-8B vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
MiniMaxSummary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 38.3 to 7.8.
Side by side
| Llama 3-8B | MiniMax-M2.1 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 25.5 | 38.9 |
| Released | 2024-04-18 | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 34 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Llama 3-8B: 31.0 (#289), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1152 | 1421 |
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3-8B: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning MiniMax-M2.1 leads
Llama 3-8B: 14.3 (#326), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math MiniMax-M2.1 leads
Llama 3-8B: 8.8 (#323), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1151 | 1397 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge MiniMax-M2.1 leads
Llama 3-8B: 7.8 (#308), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1113 | 1431 |
| GPQA Diamond | 26.1% | — |
| Vectara Hallucination Rate | — | 11.8% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual MiniMax-M2.1 leads
Llama 3-8B: 30.8 (#261), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1098 | 1378 |
| LMArena Chinese | 1076 | 1430 |
| LMArena French | 1159 | 1404 |
| LMArena German | 1104 | 1381 |
| LMArena Japanese | 967 | 1287 |
| LMArena Korean | 1004 | 1298 |
| LMArena Russian | 1109 | 1387 |
| LMArena Spanish | 1173 | 1397 |
Instruction Following MiniMax-M2.1 leads
Llama 3-8B: 58.4 (#260), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1400 |
Long Context MiniMax-M2.1 leads
Llama 3-8B: 34.2 (#251), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1128 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Llama 3-8B: 37.5 (#256), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Llama 3-8B | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1166 | 1392 |
| LMArena Creative Writing | 1150 | 1361 |
| LMArena Multi-Turn | 1152 | 1396 |
Frequently asked questions
Is Llama 3-8B better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 25.5 on the Noometry Index.
Is Llama 3-8B or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and MiniMax-M2.1 share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and MiniMax-M2.1 has 22.